---
id: gh-ads-math
name: "ads-math"
url: https://skills.yangsir.net/skill/gh-ads-math
author: agricidaniel
domain: finance
tags: ["ads", "paid-media", "financial-modeling", "cpa", "roas"]
install_count: 2400
rating: 4.30 (120 reviews)
github: https://github.com/agricidaniel/claude-ads/tree/main/skills/ads-math
---

# ads-math

> 此技能用于付费媒体财务建模，可快速计算CPA、CPL、ROAS、收支平衡点等关键指标，并自动生成敏感度分析与决策建议。适用于广告优化师、财务分析师进行预算预测与效果评估，大幅减少手动计算与核对时间。

**Stats**: 2,400 installs · 4.3/5 (120 reviews)

## Before / After 对比

### 付费媒体指标计算

**Before**:

在没有这个技能之前，广告优化师需要手动在Excel中输入多个公式，逐一核对数据源、单位换算和分母有效性，每次计算一个ROAS或CPA模型平均耗时30分钟，且容易因公式错误或数据遗漏导致结果偏差。

**After**:

此技能只需提供关键参数，即可自动验证输入、计算基础/悲观/乐观情景，并输出格式化结果与决策建议。单次建模时间从30分钟降至5分钟，且消除了计算错误。

| Metric | Before | After | Change |
|---|---|---|---|
| 计算时间 | 30分钟 | 5分钟 | -83% |

## Readme

# Paid Media Financial Model

1. Identify the decision and collect units, currency, period, tax/refund treatment,
   margin, attribution basis, and uncertainty.
2. Show the formula and map every input to an operator value or cited artifact.
3. Validate denominators, sign, missing values, incompatible windows, and unit
   conversions.
4. Calculate base, downside, and upside cases where uncertainty affects the decision.
5. Keep platform-attributed revenue, blended business revenue, cash flow, and
   contribution margin distinct.
6. Return machine-readable inputs, formulas, outputs, sensitivities, and decision
   implications.

Never fabricate missing financial inputs, hide division-by-zero, or present a point
forecast without its assumptions.



---
*Source: https://skills.yangsir.net/skill/gh-ads-math*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-ads-math/markdown*